social-dilemmas

Tag

Cards List
#social-dilemmas

Discovering Cooperative Pipelines: Autoresearch for Sequential Social Dilemmas

Hugging Face Daily Papers · 2026-05-28 Cached

This paper presents a two-level autoresearch framework where an outer-loop AI agent autonomously optimizes inner-loop LLM policy-synthesis pipelines for multi-agent sequential social dilemmas, achieving superior performance and discovering objective-specific mechanisms like fairness under a maximin welfare objective.

0 favorites 0 likes
#social-dilemmas

@omarsar0: // The Memory Curse in LLM Agents // (bookmark it) Long histories apparently degrades agents as they become increasingl…

X AI KOLs Following · 2026-05-11 Cached

This research paper identifies the 'memory curse' in LLM agents, demonstrating that expanded context windows systematically degrade cooperative behavior in multi-agent social dilemmas by eroding forward-looking intent. The authors show that targeted fine-tuning, synthetic memory sanitization, and reducing explicit Chain-of-Thought reasoning can effectively mitigate this behavioral decay.

0 favorites 0 likes
← Back to home

Submit Feedback